基于多源遥感与地形信息的北极城镇用地信息提取

doi:10.12082/dqxxkx.2019.180536

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (6): 969-982.doi: 10.12082/dqxxkx.2019.180536

• 遥感科学与应用技术 • 上一篇

基于多源遥感与地形信息的北极城镇用地信息提取

梁立^1,²(), 李鑫杨³, 刘庆生^1,^*(), 刘高焕¹, 黄翀¹, 李贺¹

1. 中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室,北京 100101
2. 中国科学院大学,北京 100049
3. 内蒙古赤峰气象局,赤峰 024000

收稿日期:2018-10-22 修回日期:2019-01-24 出版日期:2019-06-15 发布日期:2019-06-15
通讯作者: 刘庆生 E-mail:liangl.16s@igsnrr.ac.cn;liuqs@lreis.ac.cn
作者简介:
作者简介：梁立（1994-）,男,河南漯河人,硕士,研究方向为遥感和地理信息系统应用。E-mail: liangl.16s@igsnrr.ac.cn
基金资助:
国家重点研发计划课题（2016YFC1402701）、国家自然科学基金项目（41801354）

Extraction of Arctic Urban Land Use Information based on Multi-source Remote Sensing and Topograph

Li LIANG^1,²(), Xinyang LI³, Qingsheng LIU^1,^*(), Gaohuan LIU¹, Chong HUANG¹, He LI¹

1. State Key Lab of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Weather bureau of Chifeng, Chifeng 024000, China

Received:2018-10-22 Revised:2019-01-24 Online:2019-06-15 Published:2019-06-15
Contact: Qingsheng LIU E-mail:liangl.16s@igsnrr.ac.cn;liuqs@lreis.ac.cn
Supported by:
National Key Research and Development Program of China, No.2016YFC1402701;National Natural Science Foundation of China, No.41801354

摘要/Abstract

摘要：

北极城镇空间信息对于研究北极,认识北极,利用北极都有重要意义。本文以北极圈内的城市特罗姆瑟为例,使用Landsat影像、DMSP/OLS夜间灯光、ASTER-GDEM2数据,通过特征提取得到属于光谱特征、纹理特征、夜间灯光特征、地形特征等18个特征,识别最优特征组合后基于AdaBoost算法提取1990、2004、2016年研究区的城镇用地,并将提取结果与最大似然法进行了对比,在此基础上进行了扩张分析。研究结果表明：引入地形与夜间灯光特征都可以在光谱纹理特征的基础上提高提取精度。基于光谱与纹理特征得到的总体精度与kappa值分别为86.20%和0.68;加入地形特征后精度分别提高2.70%（OA）和6.21%（kappa）;加入夜间灯光特征后精度分别提高2.10%和0.50;加入地形与夜间灯光特征精度分别提高3.70%和8.55%,因此光谱、纹理、地形与夜间灯光的组合是最优特征组合。通过最优特征组合进行AdaBoost城镇提取,比最大似然法对城镇的两分类总体精度高10%左右、kappa值高20%左右。计算结果显示,研究区城镇扩张强度为5.5×10^-4左右,属于缓慢扩张;扩张的平均动态度水平为0.018,是全球水平（0.0325）的一半左右;2004-2016年的动态度水平低于1990-2004年的动态度水平,说明研究区目前由高速发展期向平稳发展期过渡。

关键词: 机器学习, Landsat, DMSP/OLS夜间灯光, DEM, 城镇提取, 特罗姆瑟, 北极城镇

Abstract:

As climate warms up and ice melts, the Arctic is drawing much more attention. It is undeniable that Arctic urban spatial information is critical for studying, understanding, and exploring the Arctic. Due to the special geographical situation, Arctic urban extraction has unique difficulties such as urban fragmentation and confusion with bare mountains. To overcome the problems of extracting Arctic urban, multi-source data including Landsat, DMSP/OLS, and ASTER-GDEM2 were used. Spectral features, texture features, nighttime light features, and topographic features were obtained after feature extraction. Apart from that, the AdaBoost algorithm was used to extract the urban areas at 1990, 2004 and 2016. To clearly and more completely understand the function of each feature, we divided features into four different groups, and compared their differences. The result shows that, adding terrain features or nighttime lighting features can improve the extraction accuracy, and that the combination of spectrum, texture, terrain, and nighttime lighting is the optimal combination of features. The overall accuracy (OA) and kappa values based on spectral and texture features are 86.20% and 0.68, respectively. After adding terrain feature, the accuracy increased by 2.7% (OA) and 6.21% (kappa) respectively. When only adding nighttime lighting feature, OA increased by 2.1% and kappa 0.50. The best result was reached when we added terrain feature and nighttime lighting simultaneously. In this case, the overall accuracy and kappa increased by 3.7% and 8.55%, respectively. So, it is the optimal combination of features. After identifying the optimal feature combination, the maximum likelihood method was used to extract urban areas to prove the effectiveness of the AdaBoost algorithm. Experiment results show that, with the optimal feature combination, extraction based on AdaBoost has its OA and kappa value 10% and 20% higher respectively than those by the maximum likelihood method. Finally, the urban expansion was analyzed. The intensity of the urban expansion in the study area is around 4.4×10^-3 from 1990 to 2004 and this number is 4.5×10^-3 from 2004 to 2016, which can be interpreted as slow expansion. The average level of expansion is 0.018, 1/2 of the global average. The urban expansion level between 1990 and 2004 is higher than that between 2004 and 2016. The difference in the dynamics during 1990-2004 and during 2004-2016 indicates that the study area is currently transitioning from a high-speed development period to a stable development period. Given the warming of the Arctic and the growing of population, Arctic urban is expected to continue expanding slowly.

Key words: AdaBoost algorithm, landsat, DMSP/OLS, DEM, urban extraction, Troms?, Arctic town

梁立, 李鑫杨, 刘庆生, 刘高焕, 黄翀, 李贺. 基于多源遥感与地形信息的北极城镇用地信息提取[J]. 地球信息科学学报, 2019, 21(6): 969-982.DOI:10.12082/dqxxkx.2019.180536

Li LIANG, Xinyang LI, Qingsheng LIU, Gaohuan LIU, Chong HUANG, He LI. Extraction of Arctic Urban Land Use Information based on Multi-source Remote Sensing and Topograph[J]. Journal of Geo-information Science, 2019, 21(6): 969-982.DOI:10.12082/dqxxkx.2019.180536

图/表 21

图1

表1

表2

光谱特征指数及计算方法"

光谱特征	公式	编号	说明
归一化植被指数NDVI	$NDVI = ρ NIR - ρ RED ρ NIR + ρ RED$	（1）	利用植被指数区分植被与城镇
增强型植被指数EVI	$EVI = 2.5 × ρ NIR - ρ RED ρ NIR + 6.0 ρ RED - 7.5 ρ BLUE + 1$	（2）	相较于NDVI,EVI对土壤背景变化敏感,能帮助区分稀疏植被与人造地表
土壤调整植被指数SAVI	$SAVI = ρ NIR - ρ RED ρ NIR + ρ RED + L · (1 + L)$	（3）	SAVI可以在研究区植被覆盖较低的地区降低土壤背景的影响,依旧作为NDVI指数对于区分植被与城镇的补充指标
归一化水体指数NDWI	$NDWI = ρ GREEN - ρ NIR ρ GREEN + ρ NIR$	（4）	用以区分水体与城镇
归一化雪被指数NDSI	$NDSI = ρ GREEN - ρ SWIR 1 ρ GREEN + ρ SWIR 1$	（5）	NDSI通过组合绿光波段 $ρ GREEN$ 及短波红外波段 $ρ SWIR 1$ 对图像的雪被信息进行增强
归一化建筑指数NDBI	$NDBI = ρ SWIR 1 - ρ NIR ρ SWIR 1 + ρ NIR$	（6）	最常用的城镇用地识别指标,城镇用地的 $ρ NIR$ 与 $ρ SWIR 1$ 反射率值变高的同时其他地类反射率值变低,呈相反趋势,所以NDBI可有效识别城镇类别
归一化差值不透水面指数NDISI	$NDISI = ρ TIR - [(ρ VIS + ρ NIR + ρ MIR) / 3] ρ TIR + [(ρ VIS + ρ NIR + ρ MIR) / 3]$	（7）	$ρ VIS$ 代表可见光红、蓝、绿3个波段中的任何一个（本文选择了红光波段）。 $ρ MIR$ 可将土壤与道路、建筑物等不透水面进行区分, $ρ VIS$ 可区分道路、建筑物等不透水面与水体

表2

图2

表3

纹理特征指数及计算方法"

纹理特征	公式	编号	说明
均值 Mean	$μ i = ∑ i, j = 0 N - 1 (P i, j)$	（8）	帮助寻找突变区域,有利于零星居民点的提取
协方差Variance	$σ i 2 = ∑ i, j = 0 N - 1 P i, j (i - μ i) 2 σ j 2 = ∑ i, j = 0 N - 1 P i, j (j - μ j) 2$	（9）	显示突变程度,辅助均值信息排除干扰像元
协同性Homogeneity	$HOM = ∑ i, j = 0 N - 1 P i, j 1 + (i - j) 2$	（10）	协同性其大小表征纹理信息的同质性,HOM值若大表示指定窗口的图像灰度矩阵总体变化小,灰度均匀
对比度Contrast	$CON = ∑ i, j = 0 N - 1 P i, j (i - j) 2$	（11）	其大小表征了影像清晰程度和局部纹理深与浅,及图像灰度差。CON值高表示指定窗口的图像灰度矩阵纹理深则显示出来的图像辨识度高
相异性Dissimilarity	$DIS = ∑ i, j = 0 N - 1 P i, j i - j$	（12）	相异性与对比度比较相似,表征了灰度差绝对值的大小,呈现线性趋势。CON越高则DIS越高
熵Entropy	$ENT = ∑ i, j = 0 N - 1 P i, j (- ln P i, j)$	（13）	熵表征了图像灰度均匀性,换句话说就是纹理的丰富程度,若局部图像的所有像元的灰度值相等,则无纹理信息,ENT=0;若指定窗口的图像灰度矩阵灰度变化大,则纹理信息丰富、纹理信息复杂则ENT越大
角二阶矩Angular Second Moment	$ASM = ∑ i, j = 0 N - 1 (P i, j) 2$	（14）	角二阶距又名能量,是指定窗口的图像灰度矩阵灰度值的平方和,其表征了图像中纹理特征的粗与细。当ASM大时,纹理特征粗大,ASM小时,纹理特征细小
相关性Correlation	$COR = ∑ i, j = 0 N - 1 P i, j (i - m i) (j - m j) σ i 2 σ j 2$	（15）	相关性表征了指定窗口的图像灰度矩阵像元值的相似性度量。图像中存在纹理信息的位置对应的COR值大于不存在纹理信息位置的COR值

表3

图3

图4

图5

表4

图6

表5

图7

图8

表6

图9

表7

图10

表8

图11

图12

表9

参考文献 27

[1]	王浩,卢善龙,吴炳方,等.不透水面遥感提取及应用研究进展[J].地球科学进展,2013,28(3):327-336
	[ Wang H, Lu S L, Wu B F, et al.Advances in remote sensing of impervious surfaces extraction and its applications[J]. Advances in Earth Science, 2013,28(3):327-336. ]
[2]	Schoettker A B, Over M, Braun M, et al.Monitoring statewide urban development using multitemporal multisensoral satellite data covering a 40-year time span in north Rhine-Westphalia(Germany)[C]// Remote Sensing. International Society for Optics and Photonics, 2004.
[3]	Watanabe M, Thapa R B, Ohsumi T, et al.Detection of damaged urban areas using interferometric SAR coherence change with PALSAR-2[J]. Earth Planets & Space, 2016,68(1):131.
[4]	柴宝惠,李培军,张瑞洁,等.基于Landsat数据和DMSP/OLS夜间灯光数据的城市扩展提取:以天津市为例[J].北京大学学报(自然科学版),2016,52(3):475-485 doi: 10.13209/j.0479-8023.2015.138
	[ Chai B H, Li P J, Zhang R J, et al.Urban expansion extraction using Landsat series data and DMSP/OLS nighttime light data: A case study of Tianjin area[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2016,52(3):475-485. ] doi: 10.13209/j.0479-8023.2015.138
[5]	陈征,胡德勇,曾文华,等.基于TM图像和夜间灯光数据的区域城镇扩张监测——以浙江省为例[J].国土资源遥感,2014,26(1):83-89 doi: 10.6046/gtzyyg.2014.01.15
	[ Chen Z, Hu D Y, Zeng W H, et al.TM image and nighttime light data to monitoring regional urban expansion: A case study of Zhejiang Province[J]. Remote Sensing For Land & Resources, 2014,26(1):83-89 ] doi: 10.6046/gtzyyg.2014.01.15
[6]	徐涵秋. 一种快速提取不透水面的新型遥感指数[J].武汉大学学报·信息科学版,2008,33(11):1150-1153
	[ Xu H Q.A new remote sensing index for fastly extracting impervious surface information[J]. Geomatics and Information Science of Wuhan University, 2008,33(11):1150-1153. ]
[7]	徐涵秋,杜丽萍.遥感建筑用地信息的快速提取[J].地球信息科学学报,2010,12(4):574-579
	[ Xu H Q, Du L P.Fast extraction of built-up land information from remote sensing Imagery[J]. Journal of Geo-information Science, 2010,12(4):574-579. ]
[8]	查勇,倪绍祥,杨山.一种利用TM 图像自动提取城镇用地信息的有效方法[J].遥感学报,2003,7(1):37-40 doi: 10.11834/jrs.20030107
	[ Zha Y, Ni S X, Yang S.An effective approach to automatically extract urban Land-use from TM Imagery[J]. Journal of Remote Sensing, 2003,7(1):37-40. ] doi: 10.11834/jrs.20030107
[9]	付乾坤,吴波,汪小钦,等.基于形态学建筑物指数的城市建筑物提取及其高度估算[J].遥感技术与应用,2015,30(1):148-154 doi: 10.11873/j.issn.1004-0323.2015.1.0148
	[ Fu Q K, Wu B, Wang X Q, et al.Building extraction and its height estimation over urban areas based on morphological building index[J]. Remote Sensing Technology and Application, 2015,30(1):148-154. ] doi: 10.11873/j.issn.1004-0323.2015.1.0148
[10]	任金华,吴绍华,周生路,等.城市不透水面遥感研究进展[J].国土资源遥感,2012,24(4):8-15 doi: 10.6046/gtzyyg.2012.04.02
	[ Ren J H, Wu S H, Zhou L S, et al.Advances in remote sensing research on urban impervious surface[J]. Remote Sensing for Land ＆ Resources, 2012,24(4):8-15. ] doi: 10.6046/gtzyyg.2012.04.02
[11]	Qiu X M, Wu S S,Miao X.Incorporating road and parcel data for object-based classification of detailed urban land covers from NAIP images[J]. Mapping Sciences & Remote Sensing, 2014,51(5):498-520.
[12]	Civco D, Chabaeva A, Parent J. KH-series satellite imagery and Landsat MSS data fusion in support of assessing urban land use growth[J]. Proc Spie, 2009,7478:74780I(1-12).
[13]	Matthias Braun.Mapping imperviousness using NDVI and linear spectral unmixing of ASTER data in the Cologne-Bonn region (Germany)[J]. Proc Spie, 2004,12(12):274-284.
[14]	Rashed T, Weeks J R, Roberts D, et al.Measuring the physical composition of urban morphology using multiple endmember spectral mixture models[J]. Photogrammetric Engineering & Remote Sensing, 2003,69(9):1011-1020.
[15]	李彩丽,都金康,左天惠.基于高分辨率遥感影像的不透水面信息提取方法研究[J].遥感信息,2009(5):36-40
	[ Li C L, Du J K, Zuo T H, The study of extracting impervious surface information based on high-resolution remote sensing Image[J]. Remote Sensing Information, 2009(5):36-40. ]
[16]	Zhifeng Liu,Chunyang He,Qiaofeng Zhang,et al.Extracting the dynamics of urban expansion in China using DMSP-OLS nighttime light data from 1992 to 2008[J]. Landscape and Urban Planning, 2012,106(1):62-72.
[17]	Konstantinov P, Baklanov A, Varentsov M, et al.Experimental urban heat island research of four biggest polar cities in northern hemisphere[C]// Geophysical Research Abstracts, Egu General Assembly, 2014.
[18]	高程程,惠晓威.基于灰度共生矩阵的纹理特征提取[J].计算机系统应用,2010,19(6):195-198
	[ Gao C C, Hui X W.GLCM-Based texture feature extraction[J]. Computer Systems & Applications, 2010,19(6):195-198. ]
[19]	Robert M H,Karthikeyan S.Textural features for image classification[J]. IEEE Transactions on systems, man, and cybernetics, 1973(6):610-621.
[20]	Hall-Beyer M.Practical guidelines for choosing GLCM textures to use in landscape classification tasks over a range of moderate spatial scales[J]. International Journal of Remote Sensing, 2017,38(5):1312-1338.
[21]	Xu Y, Tang Q, Fan J, et al.Assessing construction land potential and its spatial pattern in China[J]. Landscape and Urban Planning, 2011,103(2):207-216.
[22]	Christopher S, Francesca P, Christopher D E.Spatial analysis of global urban extent from DMSP-OLS night lights[J]. Remote Sensing of Environment, 2005,96(3-4):277-291.
[23]	Yoav Freund,Robert E Schapire.A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of computer and system sciences, 1997,55(1):119-139.
[24]	Batty M.Exploring Isovist fields: Space and shape in architectural and urban morphology[J]. Environment and Planning B: Planning and Design, 2001,28(1):123-150.
[25]	刘纪远,王新生,庄大方.凸壳原理用于城市用地空间扩展类型识别[J].地理学报,2003,58(6):885-892
	[ Liu J Y, Wang X S, Zhuang D F.Application of convex hull in identifying the types of urban land expansion[J]. Acta Geographica Sinica, 2003,58(6):885-892. ]
[26]	刘盛和,吴传钧,沈洪泉.基于GIS的北京城市土地利用扩展模式[J].地理学报,2000,55(4):407-416
	[ Liu S H, Wu C J, Shen H Q.A GIS based model of urban land use growth in Beijing[J]. Acta Geographica Sinica, 2000,55(4):407-416. ]
[27]	Angel S, Parent J, Civco D L, et al.The dimensions of global urban expansion: Estimates and projections for all countries, 2000-2050[J]. Progress in Planning, 2011,75(2):53-107.

	训练样本		测试样本
年份	城镇	非城镇	城镇	非城镇
1990	4458	21 914	265	735
2004	4076	21 452	272	728
2016	4225	20 855	327	673

分类类别	真实类别
分类类别	城镇	非城镇
城镇	249	78
非城镇	60	631
总体精度/%	86.20
Kappa值	0.68

分类类别	真实类别
分类类别	城镇	非城镇
城镇	262	65
非城镇	46	627
总体精度/%	88.90
Kappa值	0.74

分类类别	真实类别
分类类别	城镇	非城镇
城镇	262	65
非城镇	52	621
精度/%	88.30
kappa值	0.73

	真实类别
分类类别	城镇	非城镇
城镇	268	59
非城镇	42	631
总体精度/%	89.90
kappa值	0.77

基于多源遥感与地形信息的北极城镇用地信息提取

Extraction of Arctic Urban Land Use Information based on Multi-source Remote Sensing and Topograph

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献 27

相关文章 15

Metrics

本文评价

推荐阅读 0

年份	面积 /hm²	紧凑度	扩张速度/(hm²/y)	扩张强度	动态度
1990	2174.7	0.01917	-	-	-
2004	2767.0	0.02091	42.31	0.044	0.01946
2016	3291.7	0.02411	43.72	0.045	0.01580

[1]	帅艳民, 马现伟, 曲歌, 邵聪颖, 刘涛, 刘守民, 黄华兵, 谷玲霄, 拉提帕·吐尔汗江, 梁继, 李玲. 协同多时相波谱特征的不透水面信息级联提取[J]. 地球信息科学学报, 2021, 23(1): 171-186.
[2]	刘明杰, 徐卓揆, 郜允兵, 杨晶, 潘瑜春, 高秉博, 周艳兵, 周万鹏, 王凌. 基于机器学习的稀疏样本下的土壤有机质估算方法[J]. 地球信息科学学报, 2020, 22(9): 1799-1813.
[3]	陈昂, 杨秀春, 徐斌, 金云翔, 张文博, 郭剑, 邢晓语, 杨东. 基于面向对象与深度学习的榆树疏林识别方法研究[J]. 地球信息科学学报, 2020, 22(9): 1897-1909.
[4]	蒲东川, 王桂周, 张兆明, 牛雪峰, 何国金, 龙腾飞, 尹然宇, 江威, 孙嘉悦. 基于独立成分分析和随机森林算法的城镇用地提取研究[J]. 地球信息科学学报, 2020, 22(8): 1597-1606.
[5]	刘新, 赵宁, 郭金运, 郭斌. 基于LSTM神经网络的青藏高原月降水量预测[J]. 地球信息科学学报, 2020, 22(8): 1617-1629.
[6]	李婉, 牛陆, 陈虹, 吴骅. 基于随机森林算法的地表温度鲁棒降尺度方法[J]. 地球信息科学学报, 2020, 22(8): 1666-1678.
[7]	毛亚萍, 房世峰. 基于机器学习的参考作物蒸散量估算研究[J]. 地球信息科学学报, 2020, 22(8): 1692-1701.
[8]	罗竹, 刘凯, 张春亢, 邓心远, 马荣华, 宋春桥. DEM在湖泊水文变化研究中的应用进展[J]. 地球信息科学学报, 2020, 22(7): 1510-1521.
[9]	赵忠旭, 张燕杰, 潘影, 武俊喜, 李振男. 夜间灯光数据支持下西藏人类活动强度变化对生态系统调节服务的影响[J]. 地球信息科学学报, 2020, 22(7): 1544-1554.
[10]	吴志峰, 骆剑承, 孙营伟, 吴田军, 曹峥, 刘巍, 杨颖频, 王玲玉. 时空协同的精准农业遥感研究[J]. 地球信息科学学报, 2020, 22(4): 731-742.
[11]	李思进, 代文, 熊礼阳, 汤国安. DEM分辨率对黄土侵蚀沟形态特征表达的不确定性分析[J]. 地球信息科学学报, 2020, 22(3): 338-350.
[12]	王春, 徐燕, 江岭, 赵明伟. 规则格网DEM局地坡面凸凹性精度分析[J]. 地球信息科学学报, 2020, 22(3): 361-369.
[13]	赵尚民, 程维明, 蒋经天, 沙文娟. 资源三号卫星DEM数据与全球开放DEM数据的误差对比[J]. 地球信息科学学报, 2020, 22(3): 370-378.
[14]	张鑫港, 闫浩文, 张黎明. 一种用于DEM数据认证与篡改定位的感知哈希算法[J]. 地球信息科学学报, 2020, 22(3): 379-388.
[15]	赵明伟, 金永林, 江岭, 王春, 杨灿灿, 徐燕. 多模型协同下的城郊地区DEM构建方法研究[J]. 地球信息科学学报, 2020, 22(3): 389-398.